We provide a general framework for solving differentially private stochastic minimax optimization (DP-SMO) problems, which enables the practitioners to bring their own base optimization algorithm and use it as a black-box to obtain the near-optimal privacy-loss trade-off.

It is non-trivial to extend them to exhaustively deal with dual noises (i.e., the

OOD detection relying on pure visual information can inherit the limitations, e.g., when an OOD